© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14313
    Prev
    Next
    INDEX
    Explanations

    elements related to hybrid systems and scientific methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Composition, structure, or components

    np_acts-logits-general · gemini-2.0-flash

    composed of / consisting of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.92
    Tikang
    -0.77
    TemporalType
    -0.72
    windowFixed
    -0.60
    省市镇
    -0.57
    WebVitals
    -0.56
     Biôgrafia
    -0.56
    ترة
    -0.53
     chi̍t
    -0.53
    paramref
    -0.53
    POSITIVE LOGITS
     composed
    2.93
     comprised
    2.81
     consisting
    2.71
     comprising
    2.45
    composed
    2.44
     Composed
    2.42
     consists
    2.35
     composé
    2.24
     consisted
    2.21
     composée
    2.21
    Activations Density 0.950%

    No Known Activations